© 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. 87861
    Prev
    Next
    INDEX
    Explanations

    yahoo

    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
     Strah
    0.42
     natural
    0.40
     </
    0.40
    კ
    0.39
     breakaway
    0.38
     texts
    0.38
     teks
    0.38
     keras
    0.37
    k
    0.36
     großen
    0.36
    POSITIVE LOGITS
    oys
    0.46
    gin
    0.45
    ater
    0.44
    utral
    0.43
    jury
    0.43
    othermal
    0.43
    oted
    0.42
    oters
    0.42
    hre
    0.42
    otype
    0.41
    Activations Density 0.000%

    No Known Activations