© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65791
    Prev
    Next
    INDEX
    Explanations

    ice or snow

    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
    jes
    0.47
    ajú
    0.42
    WWW
    0.40
     শার
    0.38
     dandruff
    0.38
    áj
    0.37
    컹
    0.35
     guerr
    0.35
    allo
    0.35
     آه
    0.35
    POSITIVE LOGITS
     ice
    1.34
     Ice
    1.24
    Ice
    1.21
    冰
    1.20
    氷
    1.02
    ice
    0.93
     बर्फ
    0.91
     hielo
    0.90
     ICE
    0.89
     snow
    0.78
    Activations Density 0.063%

    No Known Activations