INDEX

Explanations

modifiers of size or amount, and words indicating sufficient quantity

oai_token-act-pair · gemini-2.0-flash

sufficiency

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

GEBURTSDATUM

-1.30

 Roskov

-1.23

PerformLayout

-1.08

 propOrder

-1.05

contentLoaded

-1.04

rungsseite

-0.96

 Мексичка

-0.95

 nakalista

-0.93

 utafitiHapana

-0.93

POSITIVE LOGITS

 simple

0.55

 quickly

0.53

 simply

0.50

or

0.48

 fleste

0.47

 point

0.47

0.46

put

0.45

 easily

0.45

Activations Density 1.207%

modifiers of size or amount, and words indicating sufficient quantity

sufficiency

No Comments

No Known Activations