© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80789
    Prev
    Next
    INDEX
    Explanations

    epsagon, ipsos, bummed

    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_0_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
    に
    1.80
    ﻟ
    1.55
    에
    1.45
    ל
    1.37
    ل
    1.23
    し
    1.23
    ྐ
    1.09
    ル
    1.06
    થી
    1.04
    ம்
    1.03
    POSITIVE LOGITS
    8
    2.08
    ing
    1.96
    4
    1.67
    7
    1.66
    9
    1.64
    s
    1.58
    1
    1.52
    6
    1.52
    ING
    1.48
    ة
    1.44
    Activations Density 0.000%

    No Known Activations