INDEX

Explanations

code snippets with diff notations

oai_token-act-pair · gemini-2.0-flash

-

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

location

-0.55

Location

-0.47

شهاد

-0.47

matchCondition

-0.45

 Location

-0.44

êng

-0.43

OfWork

-0.43

 Nadel

-0.42

skj

-0.41

BeginInit

-0.41

POSITIVE LOGITS

Personensuche

0.77

MigrationBuilder

0.71

 Exacts

0.68

Hentet

0.61

 ExecuteAsync

0.60

URDAY

0.60

Orsay

0.60

ofday

0.57

aclk

0.55

("")]

0.54

Activations Density 0.091%

code snippets with diff notations

-

No Comments

No Known Activations