© 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. 62454
    Prev
    Next
    INDEX
    Explanations

    cheetah

    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
    ли
    1.27
    は
    1.10
    ৭
    1.05
    ö
    1.02
    j
    0.99
     de
    0.98
    '
    0.93
    ৬
    0.93
    á
    0.92
    0.90
    POSITIVE LOGITS
    ra
    1.02
    น
    1.01
    तून
    0.93
    या
    0.89
    ンダ
    0.86
    สี
    0.86
    リ
    0.85
    set
    0.83
    สวย
    0.82
    ний
    0.81
    Activations Density 0.000%

    No Known Activations