© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63817
    Prev
    Next
    INDEX
    Explanations

    phone

    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_59_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
     minded
    0.40
    heti
    0.37
    imitives
    0.36
     apro
    0.35
    ahlen
    0.34
     aprob
    0.34
     جواب
    0.33
     답
    0.33
    답
    0.33
    minded
    0.33
    POSITIVE LOGITS
     phone
    2.67
     telephone
    2.45
     telefon
    2.44
     телефон
    2.38
     Phone
    2.34
    phone
    2.20
    Phone
    2.19
    telephone
    2.16
     PHONE
    2.14
    電話
    2.13
    Activations Density 0.057%

    No Known Activations