© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53152
    Prev
    Next
    INDEX
    Explanations

    know that

    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_31_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
     실시
    0.32
     GTX
    0.32
     žiad
    0.32
     pagare
    0.32
    釵
    0.31
     iMac
    0.30
    Ĥ
    0.30
     andDevice
    0.30
    タリ
    0.29
    Carousel
    0.29
    POSITIVE LOGITS
    项
    0.36
    Obst
    0.34
     എങ്ങനെ
    0.32
    ەر
    0.31
    uer
    0.31
     obvious
    0.31
     полага
    0.31
     রাই
    0.30
     टेंशन
    0.30
    𒅴
    0.30
    Activations Density 0.000%

    No Known Activations