INDEX

Explanations

phrases indicating possibility or speculation

oai_token-act-pair · gemini-2.0-flash

fit

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

 مُعرِّف

-0.60

ंदीखरीदारी

-0.59

 "..\..\

-0.53

 bezeichneter

-0.52

 Мексичка

-0.52

DllImport

-0.52

 LEYENDO

-0.51

blico

-0.51

SequentialGroup

-0.51

 MotionEvent

-0.50

POSITIVE LOGITS

fit

1.48

fit

1.14

Fit

1.09

 fits

1.01

Fit

0.95

FIT

0.89

fits

0.80

 Fits

0.79

FIT

0.73

 fitter

0.69

Activations Density 7.102%

phrases indicating possibility or speculation

fit

No Comments

No Known Activations