INDEX

Explanations

code syntax related to data structures and value setting

oai_token-act-pair · gemini-2.0-flash

Fixed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

geries

-0.59

 stages

-0.55

uric

-0.50

atier

-0.49

czego

-0.49

PageRoute

-0.49

hieu

-0.49

 colossal

-0.48

CrossOrigin

-0.48

worldwide

-0.48

POSITIVE LOGITS

<bos>

1.62

 &___

0.91

AsUp

0.82

 Jefus

0.79

MigrationBuilder

0.79

ſelf

0.76

 MonoBehaviour

0.73

 itſelf

0.73

ResumeLayout

0.72

Życiorys

0.71

Activations Density 1.799%

code syntax related to data structures and value setting

Fixed

No Comments

No Known Activations