© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2707
    Prev
    Next
    INDEX
    Explanations

    descriptive language, potentially of gruesome or disturbing scenes

    oai_token-act-pair · gemini-2.0-flash

    Descriptive, narrative storytelling

    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
    IsMutable
    -0.82
    IndentedString
    -0.75
    Lähteet
    -0.74
    Referanser
    -0.72
     سكانية
    -0.69
    LabelTagHelper
    -0.65
     surla
    -0.64
     jspb
    -0.63
    KEYCODE
    -0.63
    UserScript
    -0.63
    POSITIVE LOGITS
    ScopeManager
    0.52
     tend
    0.44
    fuss
    0.43
    tôi
    0.40
    ortive
    0.40
    CompleteListener
    0.40
     newName
    0.39
     Chant
    0.39
     tended
    0.38
    Dine
    0.38
    Activations Density 7.734%

    No Known Activations