© 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. 8541
    Prev
    Next
    INDEX
    Explanations

    the articles "a" or "an" combined with adjectives, verbs, or other nouns.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    вест
    -0.47
    اس
    -0.46
    ec
    -0.45
     مواليد
    -0.45
     etk
    -0.45
     reputations
    -0.44
    SpringRunner
    -0.43
    ULA
    -0.42
     follow
    -0.42
     vast
    -0.42
    POSITIVE LOGITS
    WebElementEntity
    0.69
     navideño
    0.65
    MigrationBuilder
    0.65
    ();)
    0.61
     userSchema
    0.60
    GEBURTSDATUM
    0.59
    ','$
    0.59
    ՚
    0.58
     $_"
    0.58
     deleteUser
    0.58
    Activations Density 4.700%

    No Known Activations