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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    code related to creatures in a game summoning or casting spells

    oai_token-act-pair · gemini-2.0-flash

    game development 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
     transfieras
    -0.86
    MigrationBuilder
    -0.76
     protoimpl
    -0.75
    bootstrapcdn
    -0.75
    PreferredItem
    -0.74
    marshaller
    -0.73
    PMailer
    -0.71
    expandindo
    -0.71
     AssemblyTitle
    -0.70
    InitVars
    -0.70
    POSITIVE LOGITS
    knock
    0.45
    いな
    0.43
    áculos
    0.41
     ANGLE
    0.41
    visor
    0.41
    dle
    0.41
    velocityY
    0.41
    angulo
    0.41
     regardant
    0.40
    पन
    0.40
    Activations Density 3.755%

    No Known Activations