© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9740
    Prev
    Next
    INDEX
    Explanations

    capital letters and numbers, especially names and dates

    oai_token-act-pair · gemini-2.0-flash

    two letter abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     RISERV
    -0.60
    uxxxx
    -0.58
     autorytatywna
    -0.58
    awtextra
    -0.57
    __*/
    -0.56
     MotionEvent
    -0.55
    +:+
    -0.55
     Савезне
    -0.54
    ########.
    -0.54
     XNUMX
    -0.54
    POSITIVE LOGITS
    CE
    0.64
    DP
    0.63
    PP
    0.62
    PA
    0.60
    PR
    0.60
    CA
    0.60
    CM
    0.60
    PHS
    0.59
    CS
    0.59
    SPC
    0.59
    Activations Density 10.401%

    No Known Activations