INDEX

Explanations

words related to finance, science, medicine,, academics, and politics.

oai_token-act-pair · gemini-2.0-flash

academic research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 myſelf

-0.82

 itſelf

-0.80

 Theſe

-0.72

 againſt

-0.69

 himſelf

-0.68

 uſed

-0.68

 themſelves

-0.68

 yourselves

-0.67

 Shaksp

-0.67

 acrylique

-0.66

POSITIVE LOGITS

ContentAsync

0.41

ksikon

0.41

Vi

0.41

 Bourgoin

0.40

glEnd

0.40

EndContext

0.40

vi

0.40

stwie

0.40

="@+

0.38

enumii

0.38

Activations Density 3.730%

words related to finance, science, medicine,, academics, and politics.

academic research

No Comments

No Known Activations