© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149526
    Prev
    Next
    INDEX
    Explanations

    `@Autowired` and `[Order]` annotations

    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_23_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
     erectile
    0.19
    釁
    0.18
    𝙜
    0.18
     traits
    0.17
    चुअल
    0.17
    인을
    0.17
     Guant
    0.17
    ਕ
    0.17
    ርዓ
    0.17
    attrib
    0.17
    POSITIVE LOGITS
    ⎜
    0.18
    දු
    0.17
     nidd
    0.17
     subunit
    0.16
     wahrscheinlich
    0.16
    дық
    0.16
     derajat
    0.16
    marginStart
    0.16
     кора
    0.16
     участок
    0.16
    Activations Density 0.001%

    No Known Activations