© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12995
    Prev
    Next
    INDEX
    Explanations

    no purpose or legitimacy

    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_40_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
     GDPPC
    0.43
    flin
    0.39
     Lint
    0.36
    褓
    0.35
    ++/
    0.35
    伝える
    0.35
     Lynx
    0.34
    iya
    0.34
     Ruler
    0.34
     मिले
    0.34
    POSITIVE LOGITS
     accountability
    0.40
    十分
    0.40
    vida
    0.40
    Dir
    0.39
    }:\
    0.39
    clipboard
    0.38
     punching
    0.38
    expertise
    0.37
     pyperclip
    0.37
     shines
    0.37
    Activations Density 0.085%

    No Known Activations