© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97145
    Prev
    Next
    INDEX
    Explanations

    tall stack

    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_14_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
     cloned
    0.48
    p
    0.46
     chosen
    0.44
    cop
    0.44
     tonight
    0.44
     flashing
    0.44
     uploaded
    0.44
     color
    0.42
     cop
    0.42
     participating
    0.42
    POSITIVE LOGITS
    gyi
    0.59
    SZ
    0.55
     மீட்டர்
    0.54
     カル
    0.54
    栥
    0.53
    𝗡
    0.53
    șit
    0.52
    нед
    0.52
     леса
    0.51
    gyz
    0.50
    Activations Density 0.000%

    No Known Activations