© 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-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84625
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ｋ
    0.44
    ziest
    0.42
     शक्यता
    0.40
     ś
    0.39
     Außerdem
    0.39
     examination
    0.38
    obacz
    0.38
    ^{+}$.
    0.38
    izienz
    0.38
     every
    0.38
    POSITIVE LOGITS
     цен
    0.40
     коопера
    0.40
    부
    0.40
    Фран
    0.39
    aughter
    0.38
     социа
    0.37
     зад
    0.37
     linebreak
    0.36
    ूं
    0.36
     ambition
    0.36
    Activations Density 0.000%

    No Known Activations