© 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. 153614
    Prev
    Next
    INDEX
    Explanations

    quadru

    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
    Service
    0.46
    Ci
    0.43
    ServiceName
    0.41
    May
    0.40
    Moore
    0.40
    ی
    0.40
    b
    0.40
    Bailey
    0.39
    Living
    0.39
    ़
    0.39
    POSITIVE LOGITS
    p
    0.71
    pio
    0.47
     transitioned
    0.46
     bolted
    0.44
    pang
    0.44
    mz
    0.43
     forged
    0.43
    pard
    0.42
    pf
    0.42
    lected
    0.41
    Activations Density 0.000%

    No Known Activations