© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4695
    Prev
    Next
    INDEX
    Explanations

    the string "od" or "OD", sometimes followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    od

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     ſhe
    -0.65
     becauſe
    -0.65
     Efq
    -0.63
     Theſe
    -0.63
     occaf
    -0.62
     Houſe
    -0.60
     Monfieur
    -0.59
     Jefus
    -0.58
     Diſ
    -0.58
    ſelf
    -0.57
    POSITIVE LOGITS
    twimg
    0.64
    Autoritní
    0.63
     GenerationType
    0.52
    исленность
    0.50
     autorytatywna
    0.50
    multirow
    0.48
     pon
    0.46
    Controllo
    0.46
    enumi
    0.45
    __*/
    0.44
    Activations Density 0.773%

    No Known Activations