© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56573
    Prev
    Next
    INDEX
    Explanations

    german 'ch' questions

    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_11_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
     bargains
    0.14
     triumphs
    0.14
    炰
    0.14
     bowels
    0.14
     vouchers
    0.13
    上
    0.13
     plugs
    0.13
     nurt
    0.13
     negatives
    0.13
    ίζ
    0.13
    POSITIVE LOGITS
     संयुक्त
    0.19
    aa
    0.19
    u
    0.17
    ın
    0.17
    z
    0.17
    ></
    0.17
    than
    0.17
    şe
    0.17
    with
    0.16
    t
    0.16
    Activations Density 0.000%

    No Known Activations