© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44200
    Prev
    Next
    INDEX
    Explanations

    config directory names

    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_13_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
    ‌تر
    0.17
     Make
    0.17
    encoding
    0.17
     Licenses
    0.17
     licensing
    0.16
     During
    0.16
    }})$
    0.16
     Licensing
    0.16
     weight
    0.16
    ngthening
    0.16
    POSITIVE LOGITS
     Infinix
    0.21
     dokład
    0.20
    Inet
    0.20
     കേ
    0.19
    .//
    0.19
     በጥ
    0.19
     жан
    0.19
     legumes
    0.19
     клетки
    0.19
     ऑन
    0.18
    Activations Density 0.007%

    No Known Activations