© 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. 261176
    Prev
    Next
    INDEX
    Explanations

    wishes for quick recovery or finding

    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
    Ava
    0.40
     स्टैट
    0.37
    }'
    0.36
    ourke
    0.36
     அவருடைய
    0.36
    漀
    0.35
     opportunistic
    0.35
     opportune
    0.35
    ////////////////
    0.34
    例
    0.34
    POSITIVE LOGITS
    ysin
    0.44
    yam
    0.44
    поли
    0.42
    galaxy
    0.40
     radiator
    0.40
     galaxy
    0.39
    ровка
    0.39
     projektu
    0.38
     radicals
    0.38
     brindar
    0.38
    Activations Density 0.001%

    No Known Activations