© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    words and phrases with strongly negative connotations.

    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
     tartalomajánló
    -0.91
    épendance
    -0.77
     تضيفلها
    -0.76
    GEBURTSDATUM
    -0.76
    Portail
    -0.75
    PyExc
    -0.74
    lankton
    -0.73
    sizeCache
    -0.71
    cokinetics
    -0.71
     surla
    -0.70
    POSITIVE LOGITS
     farthest
    0.44
     Seulement
    0.40
    Newswire
    0.40
     furthest
    0.40
     "..\..\..\
    0.40
     konsep
    0.39
    =<?
    0.39
     laiko
    0.38
     different
    0.38
     questão
    0.38
    Activations Density 2.154%

    No Known Activations