© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 611
    Prev
    Next
    INDEX
    Explanations

    the character sequence "ch" followed by a number

    oai_token-act-pair · gemini-2.0-flash

    ch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -1.04
    Билгалдахарш
    -0.97
    StoryboardSegue
    -0.95
     виправивши
    -0.88
    MigrationBuilder
    -0.83
    AsUp
    -0.82
    WriteTagHelper
    -0.80
     EconPapers
    -0.80
     nahilalakip
    -0.80
     дописавши
    -0.79
    POSITIVE LOGITS
    lerc
    0.46
     W
    0.45
    ines
    0.45
     pourrez
    0.44
     l
    0.43
    olski
    0.42
     ло
    0.41
    ide
    0.41
    ín
    0.41
    iana
    0.40
    Activations Density 2.277%

    No Known Activations