© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1966
    Prev
    Next
    INDEX
    Explanations

    international phone numbers

    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_44_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
    嗬
    0.40
     }+
    0.39
     probing
    0.38
    ३
    0.38
    Raleway
    0.37
    Rb
    0.37
    لاك
    0.36
    <unused73>
    0.35
     Learned
    0.35
    وريا
    0.35
    POSITIVE LOGITS
    9
    0.43
     ninety
    0.42
    匣
    0.40
     ৯০
    0.39
    assis
    0.38
     sustaining
    0.38
    ;',
    0.38
     Mü
    0.37
     irr
    0.36
     démar
    0.36
    Activations Density 0.001%

    No Known Activations