© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160020
    Prev
    Next
    INDEX
    Explanations

    German names

    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
    g
    1.21
     at
    1.20
    EL
    1.20
     for
    1.13
     were
    1.10
     was
    1.09
     trataro
    1.08
    efeu
    1.07
    dą
    1.02
    आई
    1.00
    POSITIVE LOGITS
    ו
    1.91
    م
    1.53
    ש
    1.33
    as
    1.30
    that
    1.27
    ం
    1.24
    ק
    1.23
    ம்
    1.18
    י
    1.08
    м
    1.05
    Activations Density 0.000%

    No Known Activations