© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14988
    Prev
    Next
    INDEX
    Explanations

    mentions of "I" and creating a life.

    oai_token-act-pair · gemini-2.0-flash

    personal statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.93
    ContentAsync
    -0.84
     ModelExpression
    -0.84
     MainAxisSize
    -0.82
    __*/
    -0.81
    tvguidetime
    -0.79
     transfieras
    -0.74
     ControllerBase
    -0.73
     doInBackground
    -0.73
     NSCoder
    -0.73
    POSITIVE LOGITS
     Ein
    0.47
    not
    0.45
    TH
    0.42
     Tre
    0.41
     Ju
    0.40
    lím
    0.40
     ale
    0.40
    oneof
    0.39
     poz
    0.39
     fu
    0.39
    Activations Density 0.566%

    No Known Activations