© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167423
    Prev
    Next
    INDEX
    Explanations

    regarding content safety

    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_34_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
    妙
    0.44
     отношении
    0.44
    შირ
    0.41
    䧏
    0.40
     circumstances
    0.39
     kuhusu
    0.39
    භාව
    0.38
    reth
    0.37
     situations
    0.36
    情况下
    0.36
    POSITIVE LOGITS
    Probably
    0.45
    *.
    0.42
    atributo
    0.38
     probably
    0.37
    瘀
    0.37
     tonight
    0.35
     prenda
    0.35
    𝗨
    0.35
    웹
    0.34
    *)
    0.34
    Activations Density 0.006%

    No Known Activations