INDEX

Explanations

ordinal numbers and words relating to placement or ranking

oai_token-act-pair · gemini-2.0-flash

ordinal numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Hochspringen

-0.60

لیس

-0.57

 <>",

-0.55

 دیکھیے

-0.54

Externé

-0.50

يميديا

-0.49

Personensuche

-0.49

sofa

-0.48

amilya

-0.47

 nonUne

-0.47

POSITIVE LOGITS

protoc

0.56

σμα

0.52

ripsi

0.52

anyon

0.48

writeFieldEnd

0.46

UrlResolution

0.45

glfw

0.45

addPreferredGap

0.45

IBarButtonItem

0.44

EndProject

0.44

Activations Density 0.741%

ordinal numbers and words relating to placement or ranking

ordinal numbers

No Comments

No Known Activations