© 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. 91134
    Prev
    Next
    INDEX
    Explanations

    Ot

    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
    های
    0.50
    her
    0.44
    tart
    0.43
     He
    0.42
    the
    0.42
    aim
    0.41
    f
    0.41
    nich
    0.40
    aw
    0.39
    nine
    0.39
    POSITIVE LOGITS
    තික
    0.46
    ţe
    0.46
    ţ
    0.46
    maları
    0.45
    eté
    0.44
     einf
    0.44
    ólico
    0.43
    ţional
    0.43
     ecmaVersion
    0.43
     форма
    0.42
    Activations Density 0.000%

    No Known Activations