© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219828
    Prev
    Next
    INDEX
    Explanations

    craftsmen parenthesis constructed decreases

    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_31_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
     Reward
    0.36
     reward
    0.36
    sums
    0.35
     Registers
    0.34
    銖
    0.33
    웅
    0.32
    砵
    0.32
    )}+
    0.31
     Ammonia
    0.31
     вина
    0.31
    POSITIVE LOGITS
     dringend
    0.35
     scripted
    0.35
     makarna
    0.35
     briefed
    0.34
    දේශ
    0.34
     stratég
    0.34
     échelle
    0.32
     strateg
    0.32
    否则
    0.32
     strategically
    0.32
    Activations Density 0.000%

    No Known Activations