© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126983
    Prev
    Next
    INDEX
    Explanations

    end of a sequence

    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_3_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
    在
    0.79
    ته
    0.71
    ف
    0.71
    tt
    0.70
    فة
    0.69
    制度
    0.67
    អាច
    0.67
    he
    0.67
    be
    0.67
    of
    0.66
    POSITIVE LOGITS
     cephal
    0.79
    ized
    0.75
    к
    0.72
    ᱕
    0.71
    л
    0.71
     trivially
    0.70
     dictator
    0.70
     disp
    0.69
     cookware
    0.69
     malicious
    0.68
    Activations Density 0.001%

    No Known Activations