© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12222
    Prev
    Next
    INDEX
    Explanations

    informal chatty language, especially in internet contexts

    oai_token-act-pair · gemini-2.0-flash

    Interjections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    providedIn
    -0.60
     تضيفلها
    -0.59
     autorytatywna
    -0.53
    KommentareTeilen
    -0.52
    __*/
    -0.48
    Mengapa
    -0.48
     SDLK
    -0.48
    ArgumentParser
    -0.48
     honte
    -0.48
    Sounds
    -0.47
    POSITIVE LOGITS
    TagMode
    0.67
    SourceChecksum
    0.56
    хьтан
    0.56
    ToTensor
    0.53
    PhysRev
    0.52
     jadx
    0.50
    Vidite
    0.50
    afone
    0.49
    bibitem
    0.49
    ourtney
    0.48
    Activations Density 7.530%

    No Known Activations