INDEX

Explanations

LaTeX mathematical notation

oai_token-act-pair · gemini-2.0-flash

say "$"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

}$

-0.62

 AssemblyCulture

-0.58

सन्दर्भ

-0.52

 frites

-0.49

 paulista

-0.48

 ſta

-0.48

 prada

-0.47

Redirection

-0.46

casila

-0.46

 inoxid

-0.46

POSITIVE LOGITS

0.66

_{[

0.65

_;

0.64

\}_{

0.60

_()

0.59

$.\\

0.57

MemoryWarning

0.56

[];

0.56

$.}

0.55

[]

0.55

Activations Density 26.536%

LaTeX mathematical notation

say "$"

No Comments

No Known Activations