© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13992
    Prev
    Next
    INDEX
    Explanations

    phrases including prepositions and pronouns

    oai_token-act-pair · gemini-2.0-flash

    Say "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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     zij
    -0.52
    бята
    -0.50
     sie
    -0.48
     eux
    -0.48
    彼らは
    -0.46
     she
    -0.46
    ♂
    -0.46
    edia
    -0.44
     mascul
    -0.44
     createContext
    -0.44
    POSITIVE LOGITS
     her
    1.53
    her
    0.95
     hers
    0.84
     ее
    0.84
     HER
    0.82
    Her
    0.81
    MigrationBuilder
    0.77
     её
    0.77
     Her
    0.76
    HER
    0.67
    Activations Density 10.312%

    No Known Activations