© 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. 6473
    Prev
    Next
    INDEX
    Explanations

    terms related to science fiction settings, especially names of characters, places and weapons

    oai_token-act-pair · gemini-2.0-flash

    Fantasy/Sci-fi context

    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
     chimiques
    -0.53
     étoient
    -0.51
     kvä
    -0.49
     gouvernements
    -0.48
     touristes
    -0.47
     avoient
    -0.47
     bancaire
    -0.47
     financières
    -0.47
     hendes
    -0.47
    nitten
    -0.45
    POSITIVE LOGITS
     Colossus
    0.66
    بوابة
    0.65
    Personensuche
    0.65
     Golem
    0.59
     Warden
    0.59
     gladi
    0.59
    Clan
    0.58
     autorytatywna
    0.58
    )_/¯
    0.57
     Gladiator
    0.57
    Activations Density 11.945%

    No Known Activations