© 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. 53656
    Prev
    Next
    INDEX
    Explanations

    instructions or commands

    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
     اولا
    0.37
     minore
    0.35
    CAM
    0.34
     naissance
    0.34
    ccco
    0.33
    కె
    0.33
    ➌
    0.33
     يش
    0.33
     verificare
    0.32
    anin
    0.32
    POSITIVE LOGITS
    संबंध
    0.40
    首都
    0.35
     masterpieces
    0.34
    polished
    0.33
    itelji
    0.32
    escape
    0.32
    ostream
    0.31
    íts
    0.31
    sgál
    0.31
    Invite
    0.31
    Activations Density 0.000%

    No Known Activations