© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7533
    Prev
    Next
    INDEX
    Explanations

    spanish and portuguese articles

    oai_token-act-pair · gemini-2.0-flash

    non-ASCII characters in code or text

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.78
    JvmStatic
    -0.68
    ScopeManager
    -0.63
     Thereafter
    -0.62
    )++;
    -0.61
    addCriterion
    -0.58
     Atlántico
    -0.57
     Abstand
    -0.56
     Requiem
    -0.56
    Там
    -0.56
    POSITIVE LOGITS
    migrationBuilder
    0.48
     parte
    0.45
    InstanceState
    0.42
     vostri
    0.42
    Aiheesta
    0.41
    ControllerAdvice
    0.41
    Kanpo
    0.41
    hver
    0.40
     morti
    0.40
    KURZBESCHREIBUNG
    0.39
    Activations Density 1.192%

    No Known Activations