© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    mentions of hanging and strangulation

    oai_token-act-pair · gemini-2.0-flash

    ropes

    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
     string
    -1.65
    string
    -1.47
     String
    -1.45
     strings
    -1.45
    String
    -1.39
     Strings
    -1.27
    strings
    -1.27
     rope
    -1.26
     cable
    -1.23
     STRING
    -1.20
    POSITIVE LOGITS
     Shum
    0.53
    ۜ
    0.46
     Kinders
    0.46
    onghi
    0.44
     EdgeInsets
    0.44
    Meteor
    0.43
     DbSet
    0.43
     CGRect
    0.42
     Titi
    0.42
    fromnode
    0.42
    Activations Density 2.629%

    No Known Activations