© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8198
    Prev
    Next
    INDEX
    Explanations

    sentences ending in periods, conjunctions, pronouns such as "her, him, she", and words relating to politics or court proceedings.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_token-act-pair-logits · gpt-4o-mini

    variations of "her"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оно
    -0.81
     CommonModule
    -0.77
     lady
    -0.77
     istrinya
    -0.73
     Оно
    -0.71
     nakalista
    -0.70
     woman
    -0.70
     ModelExpression
    -0.69
     quale
    -0.67
    WebServlet
    -0.66
    POSITIVE LOGITS
     her
    2.38
    her
    1.56
     hers
    1.18
    她的
    1.17
     haar
    1.15
     hennes
    1.13
     jej
    1.12
    Her
    1.11
     ее
    1.08
     suaminya
    1.05
    Activations Density 6.102%

    No Known Activations