© 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. 154194
    Prev
    Next
    INDEX
    Explanations

    telehealth telepathy

    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
    Q
    0.48
     Sint
    0.42
     Q
    0.42
    ACL
    0.41
    سون
    0.38
    g
    0.38
     Param
    0.37
    gı
    0.36
    ديد
    0.36
    蓍
    0.35
    POSITIVE LOGITS
    ase
    1.90
     approving
    0.36
    erful
    0.35
    ┄
    0.35
    kinase
    0.35
    umers
    0.34
    asek
    0.34
     presumptive
    0.34
    ioides
    0.34
    榊
    0.34
    Activations Density 0.027%

    No Known Activations