© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    sentences containing the pronoun "you" or "we" expressing a personal opinion or desire.

    oai_token-act-pair · gemini-2.0-flash

    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
    IsMutable
    -0.78
    InputTagHelper
    -0.76
    stateProvider
    -0.73
     saites
    -0.73
     BorderSide
    -0.72
     MotionEvent
    -0.72
    DockStyle
    -0.71
     fieldNum
    -0.69
     Roskov
    -0.68
     Италијани
    -0.67
    POSITIVE LOGITS
    })));
    0.47
    //
    0.44
    وض
    0.44
     tyd
    0.43
     ucapnya
    0.42
    OrderItem
    0.41
     eksempel
    0.40
    Fatalf
    0.40
     sam
    0.39
    ภูมิ
    0.39
    Activations Density 15.589%

    No Known Activations