© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    apparently finds snippets of texts in other languages

    oai_token-act-pair · 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
    __":
    -0.69
     Humanos
    -0.60
     chofe
    -0.57
    ształ
    -0.57
     puas
    -0.55
    Portale
    -0.55
    bardier
    -0.54
     encouragement
    -0.54
    __':
    -0.53
     Avez
    -0.53
    POSITIVE LOGITS
    ScopeManager
    0.68
    queryInterface
    0.57
    Personendaten
    0.56
    ğini
    0.55
    erin
    0.55
    parsedMessage
    0.55
    featureID
    0.53
    gl
    0.52
    ünün
    0.52
    VersionUID
    0.50
    Activations Density 1.913%

    No Known Activations