Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4571
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    𝗱
    2.12
    ी
    1.65
    𝗹
    1.63
    𝗺
    1.61
    HCR
    1.59
    𝘃
    1.57
    𝗽
    1.53
    larni
    1.52
    𝘺
    1.51
    𝗶
    1.51
    POSITIVE LOGITS
     encephal
    1.71
    }'
    1.66
     emanc
    1.56
     abbreviation
    1.50
    recyclerView
    1.48
     huddled
    1.44
     imm
    1.39
    '"
    1.37
     subsidiaries
    1.37
    }$
    1.37
    Activations Density 0.081%

    No Known Activations