© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77698
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     превра
    0.42
     मलिक
    0.39
    蝎
    0.37
     Phyllis
    0.36
     Liam
    0.36
    ujemo
    0.36
    आ
    0.36
     }))
    0.36
     Compound
    0.36
     Malcolm
    0.36
    POSITIVE LOGITS
    beiten
    0.41
     plen
    0.40
    মবার
    0.37
     usp
    0.36
     bulb
    0.35
     desp
    0.35
    osoma
    0.35
    Grat
    0.35
    USES
    0.34
    ื้อง
    0.34
    Activations Density 0.031%

    No Known Activations