© 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. 12606
    Prev
    Next
    INDEX
    Explanations

    second person pronouns coupled with helping verbs and action verbs

    oai_token-act-pair · gemini-2.0-flash

    decision making and advice

    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
     useDispatch
    -0.65
    LayoutConstraint
    -0.63
    AndroidJUnit
    -0.59
    endforeach
    -0.57
    CppMethod
    -0.57
     createSlice
    -0.56
     RouterModule
    -0.53
    SourceChecksum
    -0.52
     BECK
    -0.51
     Redondo
    -0.49
    POSITIVE LOGITS
    writeFieldEnd
    0.68
    fiddle
    0.59
    setArguments
    0.57
    ecraft
    0.56
    orphic
    0.55
    lode
    0.54
    erunner
    0.53
     reach
    0.52
    picuous
    0.51
     Hald
    0.50
    Activations Density 5.125%

    No Known Activations