© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108370
    Prev
    Next
    INDEX
    Explanations

    emblem level or mountain

    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_2_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
    '
    2.11
    .
    1.13
    1
    1.13
     remar
    0.98
     indemn
    0.96
     усили
    0.96
    کھ
    0.93
    .¹
    0.93
     inflicted
    0.93
     annunci
    0.92
    POSITIVE LOGITS
    ك
    1.48
    ع
    1.06
    }$.
    1.02
    ק
    0.99
    ри
    0.96
    يا
    0.96
    와의
    0.95
    },
    0.94
    ف
    0.94
    بو
    0.93
    Activations Density 0.001%

    No Known Activations