INDEX

Explanations

references to totals and statistics with associated numbers

oai_token-act-pair · gemini-2.0-flash

total

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

 total

-2.88

Total

-2.61

total

-2.58

 Total

-2.56

 TOTAL

-2.23

TOTAL

-2.11

 totale

-1.88

 totales

-1.69

getTotal

-1.53

 totaal

-1.48

POSITIVE LOGITS

RemoveField

0.60

ImageContext

0.57

verwijspagina

0.52

 whole

0.51

SOUNDBITE

0.50

QRect

0.49

MENAFN

0.49

 Krakowie

0.49

parsedMessage

0.48

躇

0.48

Activations Density 6.601%

references to totals and statistics with associated numbers

total

No Comments

No Known Activations