© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100255
    Prev
    Next
    INDEX
    Explanations

    sounds like fun

    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
    hspace
    0.54
    rish
    0.50
    re
    0.50
    inchi
    0.49
    コーディ
    0.49
    s
    0.49
    Glob
    0.47
    embra
    0.47
     ezingu
    0.47
    hafte
    0.47
    POSITIVE LOGITS
     automating
    0.51
     helium
    0.49
     TCP
    0.49
     $\{
    0.48
     dehyd
    0.46
     KOH
    0.45
     $\{\
    0.45
     roug
    0.45
     generating
    0.44
     حم
    0.44
    Activations Density 0.000%

    No Known Activations