© 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. 11812
    Prev
    Next
    INDEX
    Explanations

    language involving dogs and their behavior, particularly related to excitement and rewards

    oai_token-act-pair · gemini-2.0-flash

    sensations

    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
    expandindo
    -0.67
    LookAnd
    -0.65
     EconPapers
    -0.62
    UnknownFieldSet
    -0.62
     surla
    -0.60
    الحياه
    -0.60
     članak
    -0.59
     يتيمه
    -0.59
     disambiguazione
    -0.59
    peutic
    -0.58
    POSITIVE LOGITS
    ReadKey
    0.51
     Diarsipkan
    0.50
     Arhi
    0.49
     TextInputType
    0.46
    routeProvider
    0.46
     Wikiquote
    0.46
    gea
    0.45
     rebo
    0.45
    別に
    0.44
     acolo
    0.43
    Activations Density 7.648%

    No Known Activations