© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12342
    Prev
    Next
    INDEX
    Explanations

    a set of somewhat random terms but with a slight bias towards strong opinions and terms of degree, as well as discussion of storytelling and race.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    NUMX
    -0.60
    phite
    -0.60
    ngua
    -0.60
    estyles
    -0.60
    AndroidJUnit
    -0.59
     TextAlign
    -0.59
    сылкі
    -0.57
    aktery
    -0.54
    saraba
    -0.54
    cloudflare
    -0.54
    POSITIVE LOGITS
     Monfieur
    0.63
     myſelf
    0.55
     Jefus
    0.54
     themſelves
    0.52
     itſelf
    0.51
     himſelf
    0.50
     Conſ
    0.50
     ſche
    0.49
     ſeveral
    0.49
    TagMode
    0.48
    Activations Density 0.266%

    No Known Activations