© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53418
    Prev
    Next
    INDEX
    Explanations

    requests for questions

    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_30_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
    SAF
    0.38
     этому
    0.38
     안전
    0.36
     denna
    0.36
    มีการ
    0.35
     능
    0.35
     devo
    0.35
     crest
    0.35
     changer
    0.35
    មុ
    0.34
    POSITIVE LOGITS
     അതേ
    0.40
    owitz
    0.37
    した
    0.36
    Bray
    0.35
     Bork
    0.35
    gunakan
    0.34
    hospital
    0.33
    回答
    0.32
    ricate
    0.32
    ﻅ
    0.32
    Activations Density 0.006%

    No Known Activations