© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10682
    Prev
    Next
    INDEX
    Explanations

    language relating to biological processes, including promotion, causation, cellular lifespan, and methods of cellular modulation

    oai_token-act-pair · gemini-2.0-flash

    cell biology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    basicConfig
    -0.62
    ьа
    -0.61
    %)$
    -0.59
    utados
    -0.57
    [::-
    -0.56
     createState
    -0.53
     Participants
    -0.52
     Manuals
    -0.52
    Participants
    -0.51
    detectChanges
    -0.51
    POSITIVE LOGITS
     lenker
    0.69
    Personendaten
    0.63
     متعلقه
    0.61
    othelial
    0.52
    aktur
    0.52
    Diwedd
    0.49
    esez
    0.49
    CodedInputStream
    0.49
    Portale
    0.48
    tagHelperRunner
    0.47
    Activations Density 2.260%

    No Known Activations