© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24215
    Prev
    Next
    INDEX
    Explanations

    see

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    horst
    0.43
    Li
    0.40
    Owin
    0.40
     말미암
    0.37
    Holstein
    0.37
     घुल
    0.36
    _),
    0.36
     constructs
    0.36
    H
    0.36
    ジア
    0.35
    POSITIVE LOGITS
     SOUND
    0.40
     DOUBLE
    0.38
     PW
    0.37
    ':'
    0.37
    ”
    0.36
    ℙ
    0.36
    〟
    0.35
     постанов
    0.35
     зву
    0.35
     Sound
    0.35
    Activations Density 0.012%

    No Known Activations