© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206970
    Prev
    Next
    INDEX
    Explanations

    tell me

    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_25_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
    pole
    0.29
     énorm
    0.28
    faktor
    0.27
     英
    0.27
    ंत्र
    0.26
     influencia
    0.26
     seksual
    0.26
     노
    0.25
     centaines
    0.25
     जॉ
    0.25
    POSITIVE LOGITS
     Marino
    0.26
     historical
    0.24
     theirs
    0.24
    actionBarTab
    0.24
     Casimir
    0.23
    atay
    0.23
     Switch
    0.23
     사용할
    0.23
     archival
    0.23
    brack
    0.23
    Activations Density 0.001%

    No Known Activations