© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38114
    Prev
    Next
    INDEX
    Explanations

    Is it possible to

    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_3_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
    0
    0.61
    AY
    0.59
     அவருக்கு
    0.53
    onic
    0.52
     e
    0.52
    oyl
    0.52
    ffee
    0.51
    ுக்
    0.50
    sa
    0.49
     least
    0.49
    POSITIVE LOGITS
    ق
    0.71
    ]);
    0.69
    ن
    0.69
    ur
    0.68
    ش
    0.67
    });
    0.66
    ’
    0.66
    t
    0.64
    w
    0.64
    ку
    0.64
    Activations Density 0.001%

    No Known Activations