© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    telephone numbers that start with 2, 3, or 4 as the first digit in the area code

    oai_token-act-pair · gemini-2.0-flash

    phone numbers

    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
     crystallized
    -0.43
     generalization
    -0.42
     titer
    -0.38
    انظر
    -0.38
     cataly
    -0.38
     antithesis
    -0.38
     Entdecken
    -0.37
    Odor
    -0.37
     tactile
    -0.37
     theore
    -0.36
    POSITIVE LOGITS
    ⓧ
    0.84
    bootstrapcdn
    0.74
     Réponses
    0.73
     saites
    0.73
     Normdatei
    0.71
    ptonshire
    0.69
    MigrationBuilder
    0.68
     الحره
    0.68
     Affiliations
    0.67
    +#+
    0.66
    Activations Density 13.486%

    No Known Activations