© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12820
    Prev
    Next
    INDEX
    Explanations

    sentences that describe someone.

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    XmlType
    -0.59
    migrationBuilder
    -0.56
    DebuggerNonUser
    -0.56
    Gizmos
    -0.55
     LIABLE
    -0.52
     hemisphere
    -0.50
    gimento
    -0.49
    íqu
    -0.47
    uniq
    -0.46
    vature
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.87
    AsUp
    0.68
     AspNetCore
    0.64
    SizeMode
    0.64
     cherchés
    0.62
    Билгалдахарш
    0.59
    })`
    0.58
    SetItem
    0.57
     שוליים
    0.56
    הערות
    0.55
    Activations Density 3.839%

    No Known Activations