© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6371
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    prepositions and conjunctions

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

    comma

    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
    RenderAtEndOf
    -0.91
     AssemblyCulture
    -0.87
    InjectAttribute
    -0.84
     tartalomajánló
    -0.81
    __':
    -0.79
     AttributeSet
    -0.77
    SourceChecksum
    -0.76
    __":
    -0.76
    脚注の使い方
    -0.75
    uxxxx
    -0.75
    POSITIVE LOGITS
     including
    0.70
     with
    0.69
     without
    0.50
     to
    0.50
     having
    0.49
    tn
    0.49
    del
    0.49
     included
    0.49
     Including
    0.47
     supported
    0.47
    Activations Density 3.629%

    No Known Activations