© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 1085
    Prev
    Next
    INDEX
    Explanations

    words related to revealing, politics, and somewhat negative human conditions

    oai_token-act-pair · gemini-2.0-flash

    -ish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -0.68
    WebVitals
    -0.60
    Espèce
    -0.59
    躇
    -0.56
    ConstraintMaker
    -0.56
     BoxFit
    -0.55
     Signalez
    -0.55
    навли
    -0.52
    esModule
    -0.52
     насељу
    -0.51
    POSITIVE LOGITS
    ish
    1.46
    ISH
    1.13
    ishly
    0.94
    ishness
    0.88
    ishes
    0.86
     ish
    0.82
    ishing
    0.81
    ished
    0.79
    ge
    0.76
    ISHING
    0.74
    Activations Density 5.380%

    No Known Activations