© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51947
    Prev
    Next
    INDEX
    Explanations

    code and commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     McCle
    0.42
    roves
    0.38
    白天
    0.37
     ****",
    0.37
    スの
    0.36
    稃
    0.36
     नौकरियां
    0.36
     Staying
    0.35
     ಬರ
    0.35
     relembrar
    0.34
    POSITIVE LOGITS
     ます
    0.39
     (.)
    0.38
     sinister
    0.37
     ((
    0.37
    autom
    0.36
     фон
    0.35
     */
    0.34
     চলছে
    0.34
    anson
    0.34
    ahy
    0.34
    Activations Density 0.064%

    No Known Activations