© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238059
    Prev
    Next
    INDEX
    Explanations

    new to

    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_32_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
     విడుదల
    0.35
     сопрово
    0.34
    𝘯
    0.33
    OutputDir
    0.32
    ര്‍ന്ന്
    0.32
    和大
    0.32
     அவள்
    0.32
    andang
    0.31
    哽
    0.31
    吧
    0.31
    POSITIVE LOGITS
     ssize
    0.44
     comprise
    0.41
     kwest
    0.40
     inapplicable
    0.37
     manufactured
    0.37
     damaged
    0.36
     strikes
    0.35
     depre
    0.35
     engineered
    0.35
     dieser
    0.34
    Activations Density 0.003%

    No Known Activations