© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68527
    Prev
    Next
    INDEX
    Explanations

    German verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     werd
    0.38
    콰
    0.38
     vengo
    0.37
     venga
    0.37
     ве
    0.36
    볐
    0.36
     veniva
    0.36
     may
    0.36
    Deja
    0.35
     variance
    0.35
    POSITIVE LOGITS
    gehen
    0.47
    喿
    0.39
    ]\\
    0.38
    house
    0.38
    コム
    0.38
     goes
    0.38
    abyrinth
    0.38
     कहर
    0.38
     moveTo
    0.37
    enzie
    0.36
    Activations Density 0.007%

    No Known Activations