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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14488
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of clauses or sentences, or in certain idioms

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     ***!
    -0.70
    anyway
    -0.68
    but
    -0.67
     Anyway
    -0.67
    Anyway
    -0.66
     anyway
    -0.65
    ConstraintMaker
    -0.65
    новништво
    -0.64
    withstanding
    -0.62
     Anyways
    -0.62
    POSITIVE LOGITS
    
    0.56
    Brainz
    0.50
    Personendaten
    0.50
    IsMutable
    0.50
    туга
    0.50
     Normdatei
    0.49
    цездатний
    0.49
    orghini
    0.49
     typelib
    0.48
     Bíblia
    0.48
    Activations Density 17.688%

    No Known Activations