INDEX

Explanations

technical language related to immune response and biological processes

oai_token-act-pair · gemini-2.0-flash

cells

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 >=",

-0.66

الحياه

-0.51

Архівовано

-0.51

 Савезне

-0.50

hésite

-0.47

azón

-0.45

andExpect

-0.44

 felt

-0.43

 durs

-0.43

hésitez

-0.43

POSITIVE LOGITS

 cells

1.01

 cell

0.92

 Cells

0.81

cells

0.80

Cells

0.79

 Cell

0.75

cell

0.74

Cell

0.73

CELL

0.70

 CELL

0.69

Activations Density 2.607%

technical language related to immune response and biological processes

cells

No Comments

No Known Activations