© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6879
    Prev
    Next
    INDEX
    Explanations

    time of day

    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_39_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
     intermedi
    0.42
    intermedi
    0.40
    //$
    0.36
     scorsa
    0.36
    hower
    0.35
     bark
    0.35
    ủy
    0.35
    bdd
    0.35
    叒
    0.35
     빅뱅
    0.34
    POSITIVE LOGITS
     pomeriggio
    0.66
     вечером
    0.57
     morning
    0.53
     evening
    0.53
     afternoon
    0.52
    ्ञ
    0.52
    evening
    0.47
     wiecz
    0.47
     Abend
    0.46
    Evening
    0.46
    Activations Density 0.152%

    No Known Activations