INDEX

Explanations

words related to product features and functions

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SourceChecksum

-0.75

rungsseite

-0.71

 Audiodateien

-0.64

astify

-0.61

 muualla

-0.61

contentLoaded

-0.60

Билгалдахарш

-0.59

ViewChild

-0.59

 himo

-0.56

IndentedString

-0.56

POSITIVE LOGITS

pipe

0.55

pipes

0.49

culum

0.48

[]

0.47

 Kochen

0.46

dith

0.46

тифика

0.45

اديم

0.45

tagext

0.44

PDOException

0.44

Activations Density 0.412%

words related to product features and functions

code snippets

No Comments

No Known Activations