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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3964
    Prev
    Next
    INDEX
    Explanations

    single-letter prefixes, suffixes, or standalone words attached to longer words

    oai_token-act-pair · gemini-2.0-flash

    Del

    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
     GTS
    -0.52
     GPR
    -0.52
     Spyder
    -0.49
     Hummel
    -0.45
     CMM
    -0.45
     Godfrey
    -0.44
     Lyra
    -0.44
     KP
    -0.43
     Kapp
    -0.43
     Louie
    -0.42
    POSITIVE LOGITS
    McC
    1.01
     Lec
    1.00
     Ec
    0.95
    lec
    0.93
     ic
    0.93
    Ec
    0.92
     Hic
    0.92
     LEC
    0.92
     McC
    0.91
     NEC
    0.91
    Activations Density 15.276%

    No Known Activations