© 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. 85810
    Prev
    Next
    INDEX
    Explanations

    Names and initialisms

    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
    ,
    0.71
    0.67
    ig
    0.63
    us
    0.59
     =>
    0.59
     provider
    0.58
     Cartesian
    0.54
     proveedor
    0.54
     on
    0.54
     DIN
    0.53
    POSITIVE LOGITS
    و
    0.87
    대
    0.86
    ו
    0.84
    음
    0.81
    其他
    0.79
    ल
    0.78
    یل
    0.76
    drug
    0.75
    ް
    0.75
    극
    0.75
    Activations Density 0.000%

    No Known Activations