INDEX

Explanations

word fragments containing the characters "s", "p", "e", "n", "d", "i", "u", "c", "r", "o".

oai_token-act-pair · gemini-2.0-flash

words ending in sions

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

 Paglinawan

-0.62

 متعلقه

-0.60

expandindo

-0.51

Identyfik

-0.50

IUrlHelper

-0.49

pytorch

-0.47

 Pingback

-0.47

 Lacan

-0.45

TestBed

-0.44

Aktualisiert

-0.44

POSITIVE LOGITS

sions

0.76

sives

0.71

siveness

0.69

sively

0.68

sión

0.67

 sion

0.67

sional

0.66

sive

0.66

sion

0.66

siones

0.63

Activations Density 0.804%

word fragments containing the characters "s", "p", "e", "n", "d", "i", "u", "c", "r", "o".

words ending in sions

No Comments

No Known Activations