© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6233
    Prev
    Next
    INDEX
    Explanations

    maximum value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     AEW
    0.48
     Mascot
    0.40
    ync
    0.40
    rew
    0.38
    лок
    0.38
     Kenyatta
    0.37
     नॉर्थ
    0.37
    蔚
    0.37
    砸
    0.36
    沨
    0.36
    POSITIVE LOGITS
     gain
    0.87
    Gain
    0.84
    gain
    0.82
     Gain
    0.79
     gains
    0.73
     Gains
    0.69
    GAIN
    0.68
     amplitudes
    0.67
     gained
    0.64
     ампли
    0.63
    Activations Density 0.157%

    No Known Activations