© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81402
    Prev
    Next
    INDEX
    Explanations

    ific suffix words

    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
    اک
    1.55
    ना
    1.50
    ﻭ
    1.28
    含ま
    1.23
    なら
    1.23
    なり
    1.20
    しみ
    1.20
    m
    1.19
    した
    1.17
    りで
    1.17
    POSITIVE LOGITS
     I
    1.75
     an
    1.53
    L
    1.38
    т
    1.34
     with
    1.33
    ING
    1.32
    ς
    1.30
     +
    1.20
    s
    1.19
     o
    1.16
    Activations Density 0.001%

    No Known Activations