© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6162
    Prev
    Next
    INDEX
    Explanations

    qualifying words or phrases that add detail or uncertainty to statements

    oai_token-act-pair · gemini-2.0-flash

    emotional states or feelings

    np_token-act-pair-logits · gpt-4o-mini

    feelings and emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    #+#
    -0.70
    ❋
    -0.63
     Réponses
    -0.58
     >=",
    -0.56
    MENAFN
    -0.53
     виправивши
    -0.53
    الإنجليزية
    -0.52
    +:+
    -0.52
    TextWatcher
    -0.52
    Хьажоргаш
    -0.51
    POSITIVE LOGITS
     aware
    0.87
     willing
    0.79
     unable
    0.77
     scared
    0.77
     embarrassed
    0.76
     worried
    0.76
     afraid
    0.75
     excited
    0.75
     able
    0.73
     frightened
    0.73
    Activations Density 7.386%

    No Known Activations