INDEX

Explanations

abbreviations and numbers relevant to data collection and study design

oai_token-act-pair · gemini-2.0-flash

punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Efq

-0.94

 doubtnut

-0.88

".

-0.73

 myſelf

-0.73

ſelves

-0.71

NUMX

-0.70

ſelf

-0.67

neſs

-0.65

$_"

-0.64

 Jefus

-0.63

POSITIVE LOGITS

Not

0.77

 Will

0.76

All

0.76

 Gonna

0.74

 Also

0.74

Is

0.74

 Most

0.73

Now

0.73

 Maybe

0.73

 Doesn

0.71

Activations Density 8.161%

abbreviations and numbers relevant to data collection and study design

punctuation

No Comments

No Known Activations