© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8055
    Prev
    Next
    INDEX
    Explanations

    the prefix "trans-".

    oai_token-act-pair · gemini-2.0-flash

    tokens containing "trans"

    np_token-act-pair-logits · gpt-4o-mini

    trans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ChildIndex
    -0.53
     opérateur
    -0.52
    skal
    -0.50
    titleMargin
    -0.49
     متحده
    -0.46
    vierung
    -0.44
     invokingState
    -0.44
     E
    -0.44
    GARET
    -0.43
     Base
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.64
     Machado
    0.60
    Билгалдахарш
    0.54
     Weyl
    0.53
    ſelf
    0.53
    MigrationBuilder
    0.53
     Huron
    0.52
     sprintf
    0.52
    Datuak
    0.51
     quelconque
    0.50
    Activations Density 0.398%

    No Known Activations