© 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. 235722
    Prev
    Next
    INDEX
    Explanations

    hunched over

    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
     большей
    0.51
    Ề
    0.49
    PI
    0.46
     väč
    0.44
    ｧ
    0.43
     HOUR
    0.42
     größeren
    0.39
    orah
    0.39
     větší
    0.39
    łki
    0.39
    POSITIVE LOGITS
    㐱
    0.40
     uncomfortable
    0.37
    tans
    0.37
    クセ
    0.36
     మహి
    0.36
     jumps
    0.36
     tran
    0.36
    लों
    0.35
     busted
    0.35
     kamu
    0.34
    Activations Density 0.004%

    No Known Activations