© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13121
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns like "his", "her", and "our" and nouns that end in 's

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    complexContent
    -0.49
    DockStyle
    -0.48
    각주
    -0.44
     yourselves
    -0.43
    tagHelperRunner
    -0.42
    tersebut
    -0.42
    kapet
    -0.41
     meis
    -0.40
     înc
    -0.39
    Teraz
    -0.39
    POSITIVE LOGITS
     <=",
    0.85
    homonymie
    0.75
    ArgsConstructor
    0.74
     INTERESAR
    0.73
    AxisAlignment
    0.69
    ContextHolder
    0.67
     Parcelable
    0.66
    ModelSerializer
    0.66
    tanleria
    0.65
     OkHttpClient
    0.65
    Activations Density 1.190%

    No Known Activations