© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168221
    Prev
    Next
    INDEX
    Explanations

    URLs containing # or / with identifiers

    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_34_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
     cooper
    0.44
    লেই
    0.40
     Akshay
    0.39
    㔹
    0.38
     Het
    0.38
     harden
    0.38
    𒃶
    0.38
    合作
    0.38
    >′</
    0.37
     коман
    0.37
    POSITIVE LOGITS
    ανο
    0.38
    opie
    0.36
     minimising
    0.36
    problems
    0.35
    끄
    0.34
    রিদ্র
    0.34
     minim
    0.33
    stim
    0.33
     reducer
    0.32
    мулятор
    0.32
    Activations Density 0.000%

    No Known Activations