© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229964
    Prev
    Next
    INDEX
    Explanations

    inc, Kac,iler

    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_6_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
    تان
    0.96
     snake
    0.88
     statue
    0.87
    تون
    0.86
     beast
    0.84
    هِ
    0.84
    רץ
    0.83
     bewildered
    0.83
    ur
    0.82
     kalau
    0.81
    POSITIVE LOGITS
    s
    1.23
    ll
    1.20
    nn
    1.20
    <0x0D>
    1.18
    this
    1.07
    </h2>
    1.03
    been
    0.99
     А
    0.99
     Ό
    0.99
    나
    0.98
    Activations Density 0.000%

    No Known Activations