© 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. 158672
    Prev
    Next
    INDEX
    Explanations

    valuations or fixations

    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
    一大
    0.98
    ులు
    0.95
    ة
    0.94
     وجہ
    0.93
    高
    0.92
    一
    0.92
     an
    0.91
    好
    0.91
     on
    0.91
    一行
    0.91
    POSITIVE LOGITS
    4
    1.59
    x
    1.55
    8
    1.45
    v
    1.41
    1
    1.29
    7
    1.28
    ll
    1.21
    6
    1.17
    lerine
    1.16
    lerden
    1.13
    Activations Density 0.005%

    No Known Activations