© 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. 50824
    Prev
    Next
    INDEX
    Explanations

    good programming practice

    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
    гова
    0.35
    ided
    0.32
     significativas
    0.31
     इंपोर्टेंट
    0.31
     betyd
    0.31
    Α
    0.30
     revê
    0.30
     ready
    0.30
     mousse
    0.30
     фаса
    0.30
    POSITIVE LOGITS
     likeness
    0.36
     величина
    0.35
     koj
    0.35
     numerals
    0.35
    डमी
    0.34
     ഭാഗ
    0.34
    ewhere
    0.33
     from
    0.33
    ⽅
    0.33
     when
    0.32
    Activations Density 0.021%

    No Known Activations