© 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. 14287
    Prev
    Next
    INDEX
    Explanations

    seemingly-random punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    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
    ⓧ
    -1.02
     wireType
    -0.91
    contentLoaded
    -0.82
    GEBURTSDATUM
    -0.80
     ProtoMessage
    -0.80
    tagHelperRunner
    -0.79
    oa̍t
    -0.79
    Personendaten
    -0.77
    FieldBuilder
    -0.77
     beginnetje
    -0.77
    POSITIVE LOGITS
    has
    0.66
    is
    0.57
     but
    0.57
     is
    0.56
     and
    0.48
    or
    0.48
    but
    0.47
     OR
    0.47
     or
    0.47
     has
    0.46
    Activations Density 11.737%

    No Known Activations