© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4357
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal interactions or relationships, whether romantic, familial, or professional.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     his
    -0.81
    彼は
    -0.80
     she
    -0.80
    NameInMap
    -0.75
     hers
    -0.75
    "><?=
    -0.74
     그는
    -0.73
     hendes
    -0.72
    she
    -0.72
     useHistory
    -0.72
    POSITIVE LOGITS
     Their
    1.30
     their
    1.30
    Their
    1.27
     they
    1.17
     They
    1.14
    their
    1.13
     loro
    1.08
     THEIR
    1.06
    They
    1.05
    彼らの
    1.03
    Activations Density 1.000%

    No Known Activations