© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154018
    Prev
    Next
    INDEX
    Explanations

    resulted in a combination

    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_23_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
     censoring
    0.37
    Ob
    0.36
     deter
    0.35
     rescuing
    0.34
    ตก
    0.34
    و
    0.34
    ו
    0.33
     correcting
    0.33
     disobey
    0.33
    claration
    0.32
    POSITIVE LOGITS
    icrobial
    0.39
    动脉
    0.34
    hetic
    0.32
    erical
    0.32
     他们
    0.32
    igraphy
    0.32
    apanicolaou
    0.32
    ensureEqual
    0.31
    ığında
    0.31
    骋
    0.31
    Activations Density 0.018%

    No Known Activations