© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121162
    Prev
    Next
    INDEX
    Explanations

    requests to contact or visit

    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_27_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
    氚
    0.41
     spesso
    0.38
    nCurr
    0.38
     майже
    0.37
     বাড়ী
    0.37
     तेंद
    0.37
    uttore
    0.37
    "+"|".
    0.37
     jugado
    0.37
     dawned
    0.37
    POSITIVE LOGITS
     arteries
    0.42
     urls
    0.41
     requests
    0.40
     directories
    0.39
     rs
    0.39
     rate
    0.38
     arterial
    0.37
     lobbies
    0.37
     URLs
    0.37
     galleries
    0.37
    Activations Density 0.000%

    No Known Activations