INDEX

Explanations

numerical data and comparisons

oai_token-act-pair · gemini-2.0-flash

at

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

 ostavi

-0.78

PerformLayout

-0.75

RegressionTest

-0.75

MethodManager

-0.69

 nahilalakip

-0.66

تفصیلات

-0.64

posedge

-0.62

SourceChecksum

-0.62

 архивлан

-0.59

aarrggbb

-0.58

POSITIVE LOGITS

at

1.90

At

1.20

At

1.17

at

1.06

 tại

0.86

0.73

AtPosition

0.72

AT

0.65

AtIndex

0.60

ats

0.60

Activations Density 3.789%

numerical data and comparisons

at

No Comments

No Known Activations