© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11314
    Prev
    Next
    INDEX
    Explanations

    phrases that use "more" to indicate a greater degree of something.

    oai_token-act-pair · gemini-2.0-flash

    terms indicating quantity or emphasis

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

    Degree comparison

    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
     very
    -0.71
     muito
    -0.66
     a
    -0.62
     quite
    -0.59
     extremely
    -0.56
     muy
    -0.54
    very
    -0.53
     VERY
    -0.51
     of
    -0.50
    Very
    -0.50
    POSITIVE LOGITS
     onOptions
    0.83
     HasFactory
    0.75
     AssemblyCulture
    0.73
    phazard
    0.72
    énario
    0.72
    AutoresizingMask
    0.71
     Normdatei
    0.70
     مشين
    0.69
     Audiodateien
    0.69
     <<<<<<<<<<<<<<
    0.69
    Activations Density 0.930%

    No Known Activations