© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10674
    Prev
    Next
    INDEX
    Explanations

    informal language used when soliciting help

    oai_token-act-pair · gemini-2.0-flash

    guys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PerformLayout
    -0.68
    QMetaType
    -0.65
    providedIn
    -0.60
     esternos
    -0.58
     doInBackground
    -0.57
    válasz
    -0.57
    MigrationBuilder
    -0.55
    UrlResolution
    -0.54
     absorción
    -0.53
     kılıf
    -0.52
    POSITIVE LOGITS
    нительно
    0.51
    Altro
    0.46
    GOTREF
    0.46
    ôm
    0.46
     Nac
    0.45
    supset
    0.45
    ganu
    0.44
    nault
    0.44
    ALD
    0.43
    cipation
    0.43
    Activations Density 16.156%

    No Known Activations