© 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. 11385
    Prev
    Next
    INDEX
    Explanations

    words describing the quality or condition of a thing or person.

    oai_token-act-pair · gemini-2.0-flash

    sensory adjectives relating to quality

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

    Senses

    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
    abetes
    -0.61
    glBindTexture
    -0.61
    queryInterface
    -0.58
    دانشنامهٔ
    -0.56
    iële
    -0.54
    WebElementEntity
    -0.53
    ruptedException
    -0.52
     мәкал
    -0.51
    fony
    -0.50
    intellij
    -0.50
    POSITIVE LOGITS
     looking
    1.17
     sounding
    1.16
    looking
    1.06
     tasting
    1.03
     smelling
    1.01
     LOOKING
    0.98
     priced
    0.97
    Looking
    0.95
     Looking
    0.90
     shaped
    0.85
    Activations Density 3.069%

    No Known Activations