© 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. 53154
    Prev
    Next
    INDEX
    Explanations

    looking for / seeking a

    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
    にく
    0.45
     услуг
    0.41
     सत्
    0.38
    렀
    0.37
     советы
    0.36
     शॉपिंग
    0.36
    romy
    0.36
     satire
    0.35
    Shopping
    0.35
     椅
    0.35
    POSITIVE LOGITS
     Volunteers
    0.46
     volunteers
    0.45
    応募
    0.44
     innovative
    0.42
    ډ
    0.42
     volunte
    0.41
     volunteer
    0.41
     Gonzales
    0.41
     musicians
    0.39
     innovators
    0.39
    Activations Density 0.000%

    No Known Activations