INDEX

Explanations

code snippets with array-like and vert-like variables and string comparisons

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_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.60

Sch

-0.58

cin

-0.56

Ver

-0.56

-0.55

zi

-0.54

Se

-0.53

tis

-0.53

POSITIVE LOGITS

AddTagHelper

1.08

webElement

0.88

mybatisplus

0.88

principalColumn

0.86

routeProvider

0.84

 للمعارف

0.82

 JpaRepository

0.81

complexContent

0.75

 Roskov

0.73

ChildScrollView

0.73

Activations Density 2.151%

code snippets with array-like and vert-like variables and string comparisons

code snippets

No Comments

No Known Activations