© 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
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    𝐣
    0.50
    🎭
    0.47
     veřej
    0.45
    ੦
    0.44
    🎫
    0.43
     ModelAndView
    0.41
     teatral
    0.41
    Ꮴ
    0.41
    ੂੰ
    0.40
    angga
    0.40
    POSITIVE LOGITS
    RadioButton
    0.43
     four
    0.42
     truncate
    0.40
     shock
    0.40
    BE
    0.39
    过
    0.39
     isoform
    0.39
    TimeZone
    0.39
     ஒன்றை
    0.39
    過
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.