© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9489
    Prev
    Next
    INDEX
    Explanations

    words associated with optimism and possibility

    oai_token-act-pair · gemini-2.0-flash

    hope

    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
     hope
    -3.14
     Hope
    -3.00
    Hope
    -2.97
    hope
    -2.91
     HOPE
    -2.81
     hopes
    -2.66
     hoped
    -2.64
    HOPE
    -2.61
     hoping
    -2.39
     Hopes
    -2.28
    POSITIVE LOGITS
    ագրություններ
    0.82
    ngdoc
    0.69
    providedIn
    0.66
    tvguidetime
    0.63
    EndGlobalSection
    0.59
    Datuak
    0.58
    __':
    0.57
    httphttps
    0.57
    KURZBESCHREIBUNG
    0.56
    üyada
    0.56
    Activations Density 3.329%

    No Known Activations