© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155138
    Prev
    Next
    INDEX
    Explanations

    and

    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_60_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
     can
    0.43
     as
    0.41
     Can
    0.39
     a
    0.38
    接続
    0.38
    can
    0.37
    )^{[\
    0.36
    ),'
    0.36
    CONNE
    0.34
     JL
    0.34
    POSITIVE LOGITS
     خواهند
    0.45
     serán
    0.45
    Has
    0.43
     I
    0.42
    but
    0.42
     terão
    0.42
    But
    0.40
    have
    0.40
     seront
    0.40
    has
    0.40
    Activations Density 0.002%

    No Known Activations