© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175802
    Prev
    Next
    INDEX
    Explanations

    iterating backwards

    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_20_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
     last
    0.45
     hailing
    0.42
     following
    0.41
     அந்த
    0.41
    l
    0.40
     cette
    0.40
     welke
    0.39
    бель
    0.38
     FOUND
    0.38
     annivers
    0.38
    POSITIVE LOGITS
     짧
    0.49
    🥹
    0.47
    thiophene
    0.47
    🫣
    0.46
     děti
    0.46
     gravar
    0.46
     sá
    0.46
     børn
    0.45
    🫤
    0.44
     Imperio
    0.44
    Activations Density 0.000%

    No Known Activations