© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218911
    Prev
    Next
    INDEX
    Explanations

    apps like

    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_31_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
    ፧
    0.37
    AW
    0.36
    тет
    0.35
     mo
    0.34
    PER
    0.34
     поза
    0.33
    yt
    0.32
    tub
    0.32
    POP
    0.32
     belieb
    0.32
    POSITIVE LOGITS
     ㄹ
    0.40
     konserv
    0.38
     Conservative
    0.35
    睒
    0.34
     constituents
    0.33
     Bedroom
    0.33
     નિય
    0.33
    下載
    0.32
     আধুনিক
    0.32
     रिवाइज
    0.32
    Activations Density 0.004%

    No Known Activations