© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192677
    Prev
    Next
    INDEX
    Explanations

    guar, gaur, gum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    at
    1.39
    a
    1.23
    ת
    1.16
    هم
    1.12
     (\
    1.12
    ה
    1.10
    }]=
    1.02
    en
    0.99
    ческие
    0.96
    ص
    0.93
    POSITIVE LOGITS
    O
    1.02
    д
    1.00
    дзі
    0.98
    á
    0.96
     výkon
    0.94
    ik
    0.88
    uk
    0.86
    த்தில்
    0.86
    държа
    0.86
    EE
    0.85
    Activations Density 0.001%

    No Known Activations