INDEX

Explanations

code and code-related documentation, including function calls, variable declarations, and layout properties

oai_token-act-pair · gemini-2.0-flash

specialized technical terms or code snippets

np_token-act-pair-logits · gpt-4o-mini

Code/file-related text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ณ์

-0.54

specialchars

-0.48

тивное

-0.47

日閲覧

-0.47

IntoConstraints

-0.46

AutoField

-0.45

Yeo

-0.44

 InputDecoration

-0.43

êmio

-0.42

henswürdigkeiten

-0.42

POSITIVE LOGITS

 purpoſe

0.59

ale

0.58

цездатний

0.58

Hentet

0.58

 religieuses

0.57

HasAnnotation

0.57

MigrationBuilder

0.56

CloseOperation

0.55

 enfans

0.53

AddTagHelper

0.53

Activations Density 0.275%

code and code-related documentation, including function calls, variable declarations, and layout properties

specialized technical terms or code snippets

Code/file-related text

No Comments

No Known Activations