© 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. 88946
    Prev
    Next
    INDEX
    Explanations

    Form

    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
     negotiated
    0.40
     zor
    0.39
    e
    0.39
     negotiations
    0.39
    おり
    0.38
     ISM
    0.38
     effortless
    0.38
     meager
    0.38
    듬
    0.37
     fede
    0.37
    POSITIVE LOGITS
    ats
    0.63
    atu
    0.59
    atian
    0.57
    atz
    0.52
    Factors
    0.52
    ATS
    0.51
     Ats
    0.50
    atile
    0.49
    atiti
    0.49
    attan
    0.49
    Activations Density 0.001%

    No Known Activations