© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9278
    Prev
    Next
    INDEX
    Explanations

    intensifiers such as "a big" or "huge" and adjectives like "first".

    oai_token-act-pair · gemini-2.0-flash

    a/an

    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
     ConstraintSet
    -0.57
     pprint
    -0.48
    kloped
    -0.47
    ьа
    -0.46
     Swallow
    -0.46
     AppColors
    -0.46
    Traceback
    -0.45
     Crimes
    -0.45
     CountDown
    -0.44
    Portale
    -0.43
    POSITIVE LOGITS
    toMatchSnapshot
    0.67
     }}"></
    0.66
    dostęp
    0.63
    LookAnd
    0.63
    omitempty
    0.57
    مصادر
    0.55
    leneck
    0.54
    simum
    0.53
    Хьажоргаш
    0.52
    ***************/
    0.51
    Activations Density 3.657%

    No Known Activations