© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123586
    Prev
    Next
    INDEX
    Explanations

    держись / придерживаться

    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
    k
    0.82
    i
    0.76
    r
    0.75
    g
    0.75
    ia
    0.75
    ιών
    0.70
    olition
    0.67
    pecific
    0.65
    git
    0.63
     які
    0.63
    POSITIVE LOGITS
    ف
    1.03
     powied
    0.77
    ش
    0.73
    に
    0.70
    ]!=
    0.69
    ]);
    0.68
     pago
    0.68
    \%$
    0.68
    大
    0.68
    š
    0.68
    Activations Density 0.000%

    No Known Activations