© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197642
    Prev
    Next
    INDEX
    Explanations

    pero che

    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_4_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
    ेक
    0.57
    it
    0.55
    as
    0.54
    IR
    0.51
     imperative
    0.50
    es
    0.49
    Ğ
    0.48
     *:
    0.48
     '':
    0.47
     OK
    0.46
    POSITIVE LOGITS
    。
    0.56
    בות
    0.56
    רי
    0.55
    ່ນ
    0.55
    ני
    0.54
     percorso
    0.53
     significato
    0.51
    Ꮨ
    0.51
    שי
    0.50
     bagno
    0.49
    Activations Density 0.000%

    No Known Activations