© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194529
    Prev
    Next
    INDEX
    Explanations

    lead to negative consequences

    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_27_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
     AGAIN
    0.42
    ྥ
    0.37
    绸
    0.36
    辖
    0.36
     Giải
    0.36
     Центра
    0.35
    瑚
    0.35
     cvec
    0.35
    ັດ
    0.34
    😋
    0.34
    POSITIVE LOGITS
     consolidate
    0.38
    Powers
    0.38
    pops
    0.38
    চারে
    0.37
    তনের
    0.37
     popping
    0.37
     scorers
    0.36
     divided
    0.36
    poons
    0.36
    変わ
    0.35
    Activations Density 0.006%

    No Known Activations