© 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. 88351
    Prev
    Next
    INDEX
    Explanations

    Carp

    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
    Son
    0.49
    Ost
    0.49
    i
    0.46
    U
    0.45
    ي
    0.45
    GCD
    0.44
    Scr
    0.44
    Urs
    0.43
    UTS
    0.43
    Is
    0.42
    POSITIVE LOGITS
    েন
    0.44
    etting
    0.43
    ্তার
    0.43
    ală
    0.43
    al
    0.43
    etam
    0.42
    en
    0.42
    エット
    0.41
    㽡
    0.41
    taking
    0.40
    Activations Density 0.000%

    No Known Activations