INDEX

Explanations

code snippets with different indentation levels

oai_token-act-pair · gemini-2.0-flash

Java code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 kasarigan

-0.79

 оригіналу

-0.77

awtextra

-0.77

 AssemblyCulture

-0.72

__":

-0.69

 Roskov

-0.69

 ExecuteAsync

-0.69

__":

-0.68

fony

-0.66

<?

-0.66

POSITIVE LOGITS

DataInputStream

0.51

 électriques

0.44

setResult

0.44

اقرأ

0.44

JsonPropertyName

0.42

iomanip

0.40

 если

0.40

drawSprites

0.39

 téléph

0.38

if

0.37

Activations Density 2.488%

code snippets with different indentation levels

Java code

No Comments

No Known Activations