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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9946
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with horror fiction

    oai_token-act-pair · gemini-2.0-flash

    horror stories

    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
     Terror
    -1.32
     terror
    -1.30
     murderous
    -1.30
     murder
    -1.23
     horror
    -1.23
     killing
    -1.23
     terrifying
    -1.21
     kill
    -1.20
    Terror
    -1.20
     Murder
    -1.19
    POSITIVE LOGITS
     prêtres
    0.50
     figliu
    0.41
    transQ
    0.40
    nuss
    0.40
     commerciales
    0.40
    mpion
    0.40
     giornal
    0.39
    guero
    0.39
     brancas
    0.39
    seamnă
    0.38
    Activations Density 1.880%

    No Known Activations