INDEX

Explanations

code snippets, especially related to data structures and biological processes

oai_token-act-pair · gemini-2.0-flash

biological and cellular processes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

脚注の使い方

-0.56

Personendaten

-0.53

RenderAtEndOf

-0.52

PerformLayout

-0.48

DockStyle

-0.47

 ब्रेकडाउन

-0.45

 CreateTagHelper

-0.43

DispatchToProps

-0.43

EndContext

-0.43

󠁴

-0.43

POSITIVE LOGITS

@[+][

0.59

スナー

0.56

TextAppearance

0.54

 isComment

0.52

 étoient

0.51

 مواليد

0.51

existsSync

0.51

ômico

0.50

řevě

0.50

sheng

0.50

Activations Density 0.393%

code snippets, especially related to data structures and biological processes

biological and cellular processes

No Comments

No Known Activations