© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161460
    Prev
    Next
    INDEX
    Explanations

    German words with umlauts

    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_2_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
    <0x80>
    0.89
     Yolanda
    0.87
     föret
    0.82
    ോക
    0.81
    ja
    0.80
    gast
    0.80
    villa
    0.80
     I
    0.79
    ographic
    0.78
     Elvis
    0.78
    POSITIVE LOGITS
    ન
    1.47
    ।
    1.39
    }
    1.18
    。
    1.16
     can
    1.11
    ।’
    1.11
    )
    1.11
    )।
    1.10
    ৬
    1.10
    "।
    1.09
    Activations Density 0.000%

    No Known Activations