© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258209
    Prev
    Next
    INDEX
    Explanations

    party leaders and names

    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_22_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
    绘
    0.49
     silencio
    0.48
     alimento
    0.46
     உர
    0.46
    براير
    0.46
    userdata
    0.44
     фай
    0.44
    FormData
    0.44
    ﻨ
    0.44
    spacerItem
    0.44
    POSITIVE LOGITS
     Klassen
    0.45
     mischief
    0.44
     Harry
    0.44
     Gruber
    0.42
     Client
    0.42
     Vil
    0.42
    ätzen
    0.42
     পদ্
    0.41
     Moż
    0.41
     Vera
    0.41
    Activations Density 0.000%

    No Known Activations