© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227858
    Prev
    Next
    INDEX
    Explanations

    DPTM or DAPT

    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_6_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
    1.47
     as
    1.15
    _
    1.07
    ate
    1.02
     by
    0.99
    =
    0.93
    dy
    0.92
     from
    0.91
    dam
    0.89
     =
    0.88
    POSITIVE LOGITS
    ра
    1.12
    し
    1.06
    ну
    1.00
    톄
    0.99
    ರ್
    0.98
    ве
    0.96
    れる
    0.96
    ру
    0.90
    ጒ
    0.87
    но
    0.86
    Activations Density 0.000%

    No Known Activations