© 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. 52624
    Prev
    Next
    INDEX
    Explanations

    teams that consistently contend

    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
     polarised
    0.44
    ന്
    0.43
    ahrt
    0.42
    柛
    0.41
     polarized
    0.38
     ато
    0.37
     patriarch
    0.36
    >(){
    0.36
    Pop
    0.36
     átomos
    0.35
    POSITIVE LOGITS
    요일
    0.39
     이후
    0.39
    삶
    0.38
     삶
    0.38
     जियो
    0.38
    மணிய
    0.35
    安心
    0.34
     Prefer
    0.34
    ርዓ
    0.34
    Lifetime
    0.34
    Activations Density 0.013%

    No Known Activations