© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38621
    Prev
    Next
    INDEX
    Explanations

    erodes trust

    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_57_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
    Collective
    0.40
    collective
    0.36
     collective
    0.34
     Collective
    0.33
     $('<
    0.33
    ilis
    0.32
    㞱
    0.32
    Finite
    0.32
    Acts
    0.32
    BAS
    0.31
    POSITIVE LOGITS
    斟
    0.40
    gente
    0.36
    िकेटेड
    0.36
    respected
    0.34
     dishwasher
    0.34
     badass
    0.33
    🍢
    0.33
    ဝ်
    0.33
     stava
    0.32
     మద్యం
    0.32
    Activations Density 0.000%

    No Known Activations