© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215384
    Prev
    Next
    INDEX
    Explanations

    social media and retailers

    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_31_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
    వంత
    0.42
    DEFAULT
    0.38
     ===
    0.36
     DEFAULT
    0.36
     default
    0.35
     barbers
    0.34
     Stateful
    0.34
     dưới
    0.34
     khúc
    0.33
     Request
    0.33
    POSITIVE LOGITS
     hanged
    0.38
    elligence
    0.36
     calcS
    0.36
     recalcul
    0.35
    做得
    0.35
     tangle
    0.35
    󠁳
    0.35
    ﯼ
    0.34
    ថ្ងៃ
    0.34
    ziff
    0.34
    Activations Density 0.002%

    No Known Activations