© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259641
    Prev
    Next
    INDEX
    Explanations

    animal legs and eyes

    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_22_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
    sin
    0.44
     Kazim
    0.43
    ss
    0.41
    εν
    0.41
    si
    0.40
    acia
    0.40
     ито
    0.39
    <0x8C>
    0.38
    식
    0.37
    圻
    0.37
    POSITIVE LOGITS
     offrant
    0.50
     micrographs
    0.48
    correcto
    0.47
    นำ
    0.44
     น้ำ
    0.44
    唰
    0.44
     implementación
    0.44
     primitives
    0.44
     Implement
    0.44
    Incorrect
    0.44
    Activations Density 0.000%

    No Known Activations