© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14020
    Prev
    Next
    INDEX
    Explanations

    a mix of past tense verbs, prepositions, maths operators, and other seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    start/appearance verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Мексичка
    -0.46
    enderror
    -0.45
    woli
    -0.45
    <eos>
    -0.44
     οποίο
    -0.43
    ::*;
    -0.39
     ease
    -0.39
    纪
    -0.39
    ;
    -0.38
    かります
    -0.38
    POSITIVE LOGITS
    Vidite
    0.90
    NUMX
    0.78
    Diweddarwch
    0.75
    __":
    0.73
    __':
    0.71
    Попис
    0.69
    Enllaces
    0.69
    <bos>
    0.69
    ]--;
    0.68
    apatalk
    0.67
    Activations Density 1.553%

    No Known Activations