© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16293
    Prev
    Next
    INDEX
    Explanations

    the letter a as a standalone word or part of a word with diacritics, possibly finding some spanish words

    oai_token-act-pair · gemini-2.0-flash

    code, commands, foreign language

    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
     who
    -0.46
    Delegate
    -0.40
    N
    -0.40
     nonetheless
    -0.40
     also
    -0.40
    ga
    -0.40
     N
    -0.39
    又
    -0.38
    েন
    -0.38
    ায়
    -0.38
    POSITIVE LOGITS
     pinulongan
    0.95
    adpleegd
    0.88
    MLLoader
    0.83
     &___
    0.81
    exitRule
    0.79
    tagHelperRunner
    0.79
    webElementGuid
    0.79
    bootstrapcdn
    0.77
    WillAppear
    0.76
     мәкал
    0.75
    Activations Density 0.224%

    No Known Activations