© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35333
    Prev
    Next
    INDEX
    Explanations

    see where this goes

    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_7_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
    F
    0.48
    o
    0.47
    P
    0.44
    N
    0.44
    G
    0.40
    V
    0.39
    O
    0.38
    D
    0.37
    U
    0.37
    C
    0.36
    POSITIVE LOGITS
    <0x80>
    0.37
     Από
    0.36
     AIS
    0.36
     opérations
    0.36
     frå
    0.35
     utilizzati
    0.35
     THIS
    0.35
     ITS
    0.35
     additives
    0.34
     ovog
    0.33
    Activations Density 0.005%

    No Known Activations