© 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. 3414
    Prev
    Next
    INDEX
    Explanations

    words related to fictional conflict between good and evil

    oai_token-act-pair · gemini-2.0-flash

    memorable

    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
     evil
    -1.53
     Evil
    -1.48
    Evil
    -1.48
    evil
    -1.44
     villain
    -1.27
     villains
    -1.13
     toxic
    -1.05
     Toxic
    -1.05
     Bad
    -1.04
     Villain
    -1.04
    POSITIVE LOGITS
     AssemblyCulture
    0.61
    NameInMap
    0.59
     Chwiliwch
    0.51
     ?>>
    0.51
    LookAnd
    0.50
     EconPapers
    0.47
    inerary
    0.46
    esModule
    0.45
     Référence
    0.45
     stimm
    0.45
    Activations Density 2.379%

    No Known Activations