© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    references to academic works like articles, projects, studies, lessons, books, or anything studied

    oai_token-act-pair · gemini-2.0-flash

    articles and reviews

    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
    oredCriteria
    -0.58
    ,:);
    -0.56
     explore
    -0.56
     overview
    -0.54
     address
    -0.52
    '},
    -0.52
     recap
    -0.52
     outline
    -0.52
     debate
    -0.51
     فريبيس
    -0.50
    POSITIVE LOGITS
    GraphicsUnit
    0.63
    帖最后由
    0.56
    viewDidLoad
    0.56
    Atsauces
    0.55
    ianum
    0.53
    SequentialGroup
    0.51
    banen
    0.51
    LayoutConstraint
    0.50
     morire
    0.50
    reactivex
    0.50
    Activations Density 5.993%

    No Known Activations