© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    code snippets with a bias toward javascript code and C preprocessor directives

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
     Offisielt
    -0.81
    NUMX
    -0.75
    équences
    -0.67
    ressee
    -0.65
     misfortune
    -0.65
    Материалы
    -0.64
    ··
    -0.62
     insensible
    -0.60
    Repost
    -0.59
    ^(@)
    -0.59
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
    Gweler
    0.62
    RegressionTest
    0.60
    AddTagHelper
    0.59
    Jereo
    0.59
    SetBool
    0.58
     typelib
    0.58
    buttonBar
    0.57
    wpi
    0.57
    Geplaatst
    0.57
    Activations Density 5.708%

    No Known Activations