© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51492
    Prev
    Next
    INDEX
    Explanations

    code and libraries

    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
    結晶
    0.36
    衰
    0.34
     хло
    0.33
     clade
    0.33
     Foli
    0.33
     diaphr
    0.33
    rmann
    0.33
     هند
    0.33
     oggetti
    0.32
    ificação
    0.31
    POSITIVE LOGITS
     //=>
    0.31
    ⟺
    0.31
    ][_
    0.31
    短期
    0.30
    钏
    0.30
    育て
    0.30
    baidu
    0.30
    Loans
    0.30
    loans
    0.30
     বোধ
    0.29
    Activations Density 0.000%

    No Known Activations