© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82929
    Prev
    Next
    INDEX
    Explanations

    ph

    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_53_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
    目は
    0.45
    目
    0.43
    目が
    0.38
    ARN
    0.37
    opoietic
    0.37
    ocation
    0.36
     დ
    0.36
    nyez
    0.36
     filing
    0.35
     reckoning
    0.35
    POSITIVE LOGITS
    ph
    1.59
     ph
    1.45
    Ph
    1.25
     Ph
    1.18
    pha
    1.13
    PH
    1.10
    φ
    1.08
     PH
    1.06
    pher
    1.05
    phs
    1.00
    Activations Density 0.003%

    No Known Activations