© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14175
    Prev
    Next
    INDEX
    Explanations

    rapper names and songs

    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_40_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
    lastCursor
    0.38
    сион
    0.37
     Singleton
    0.37
     കണ്ട
    0.37
     워
    0.36
    汴
    0.36
    Singleton
    0.36
     usc
    0.36
     나와
    0.36
    ख्त
    0.35
    POSITIVE LOGITS
    蛍
    0.41
     mixtape
    0.40
    彈
    0.40
     starve
    0.40
     mixt
    0.39
     Restaur
    0.37
     দুর্ভিক্ষ
    0.36
     starved
    0.36
     resusc
    0.36
     Juillet
    0.36
    Activations Density 0.028%

    No Known Activations