© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196828
    Prev
    Next
    INDEX
    Explanations

    positive

    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_46_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
     favours
    0.39
     Cubic
    0.39
    otransferase
    0.38
    薗
    0.37
     trudno
    0.37
     легко
    0.36
    分離
    0.36
     উপকরণ
    0.36
     fathom
    0.36
    బడి
    0.36
    POSITIVE LOGITS
     SOUND
    0.49
     sounding
    0.44
     sounded
    0.42
    SOUND
    0.41
     প্ল
    0.40
    sounding
    0.40
    Sound
    0.39
    -(
    0.38
    罗马
    0.38
     звуча
    0.38
    Activations Density 0.004%

    No Known Activations