© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209040
    Prev
    Next
    INDEX
    Explanations

    creation and response

    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_25_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
     Maryland
    0.39
     سرح
    0.37
    __);
    0.34
     several
    0.33
     director
    0.32
     드리
    0.32
     observable
    0.32
     यामुळे
    0.32
     мог
    0.32
    莠
    0.32
    POSITIVE LOGITS
     créé
    0.40
    CREATE
    0.39
     geschaffen
    0.38
    Created
    0.38
    RESPOND
    0.38
    ᱐
    0.38
     kreatif
    0.37
    CREATED
    0.37
     creatividad
    0.37
    trivial
    0.37
    Activations Density 0.006%

    No Known Activations