INDEX

Explanations

words related to the body, mind, and their states, sometimes in a spiritual or medical context.

oai_token-act-pair · gemini-2.0-flash

Body

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

 body

-1.14

 Body

-1.07

 BODY

-1.05

 bodies

-1.02

Body

-1.00

 Bodies

-0.99

body

-0.93

bodies

-0.91

Bodies

-0.85

BODY

-0.85

POSITIVE LOGITS

principalTable

0.57

 kasarigan

0.48

moveToNext

0.47

 referenties

0.46

grà

0.46

 Meksiku

0.46

nala

0.45

 مفص

0.45

TypedDataSet

0.45

vitis

0.44

Activations Density 19.982%

words related to the body, mind, and their states, sometimes in a spiritual or medical context.

Body

No Comments

No Known Activations