© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90336
    Prev
    Next
    INDEX
    Explanations

    formatting and structure

    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
     háb
    0.46
     "&
    0.41
     setShow
    0.40
    经营
    0.38
     felices
    0.37
     id
    0.37
     thrilling
    0.37
    ,=
    0.36
     grading
    0.36
    jesus
    0.36
    POSITIVE LOGITS
    ARS
    0.45
    änder
    0.41
    ab
    0.41
    aras
    0.40
    ars
    0.40
    acup
    0.39
    ayama
    0.38
    AAF
    0.38
    ip
    0.37
    abe
    0.37
    Activations Density 0.017%

    No Known Activations