© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59759
    Prev
    Next
    INDEX
    Explanations

    if condition

    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
    i
    1.00
    ent
    0.86
    enn
    0.85
    ments
    0.79
    pecific
    0.79
    <0x0D>
    0.76
    iverse
    0.75
    ifferential
    0.75
    me
    0.74
    ند
    0.73
    POSITIVE LOGITS
    Data
    0.91
    }$;
    0.85
    ק
    0.83
    KL
    0.78
    দ
    0.78
    స
    0.77
    К
    0.76
    б
    0.75
    та
    0.73
    ん
    0.71
    Activations Density 0.025%

    No Known Activations